What is Document code?

A workflow for adding useful docstrings, comments, and documentation to code that changed or is difficult to understand.

Use it to document functions, classes, and modules, explain important reasons or trade-offs, and update README or API documentation.

It helps future readers understand public interfaces, non-obvious decisions, and updated usage without relying on guesses.

Document code — Skill by AuraVixStudio

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/auravixstudio/caelo/document-code

Any agent

npx skills add AuraVixStudio/caelo --skill document-code

Clone the repo

git clone --depth 1 https://github.com/AuraVixStudio/caelo

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 241 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00017	$0.00241
Opus 5	$0.00009	$0.00120
Sonnet 5	$0.00003	$0.00048
Haiku 4.5	$0.00002	$0.00024

Measured 2d ago against content hash 324329592307, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Document code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

caelo_core/skills/builtin/document-code/SKILL.md · 28 lines

What it actually says

Document code

Use this to make code understandable to the next reader.

Steps

Understand first. Read the code until you can explain what it does and why. Don't document guesses.
Docstrings. Add/update docstrings on public functions, classes and modules: purpose, parameters, return value, and non-obvious behavior or side effects. Match the project's docstring style.
Comments where they earn their place. Explain why (intent, trade-offs, gotchas), not what the code already says. Remove stale comments.
External docs. If the change affects usage, update the README / API docs / module header accordingly.
Report. Note what you documented and anything still unclear that needs an owner.

Notes

Keep comment density consistent with the surrounding file.
User-facing docs follow the repo's language rule; internal comments follow the file.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 28 lines · 17 tokens per session scan A 324329592307

Subscribe to this mod's changes

Document code is a skill published in the GitHub repository AuraVixStudio/caelo (22 stars, last pushed 20d ago), licensed Apache-2.0. It adds 17 tokens to every session and 241 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs Creative and media Documents ai-agent byok coding-agent desktop-app electron fastapi

katra

Chronicle development work in a committed, rich-component dev log as you build. Use when starting a piece of work that should be logged, when capturing a screenshot/gif/render into the log, when adding a before/after comparison, or at commit time to stamp the active draft with its hash + diffstat. Keywords - katra…

craigjmidwinter/getvect · 88 tokens

getvect

Convert a raster image (PNG, JPEG, BMP) into a vector file (SVG, EPS, DXF, PDF) locally, with no network call and no account. Use when you have generated or been given a bitmap and need clean editable paths — a logo to scale, line art to cut, a diagram to embed at any size. Do not use for photographs you want to keep…

craigjmidwinter/getvect · 92 tokens

Document code

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Document code

Steps

Notes

What this file has done since we first saw it

Other skills, from other repositories

katra

getvect

feishu-im-read

weftcut

seedream

compose:subagent